{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T11:55:48Z","timestamp":1764244548317,"version":"3.46.0"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T00:00:00Z","timestamp":1764201600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Accurate prediction of human crowd behavior presents a significant challenge with critical implications for autonomous systems. The core difficulty lies in developing a comprehensive computational framework capable of effectively modeling the spatial-temporal dynamics through three essential components: feature extraction, attention propagation, and predictive modeling. Current spatial-temporal graph convolutional networks (STGCNs), which typically employ single-hop neighborhood message passing with optional self-attention mechanisms, exhibit three fundamental limitations: restricted receptive fields due to being confined to limited propagation steps, poor topological extensibility, and structural inconsistencies between network components that collectively lead to suboptimal performance. To address these challenges, we establish the theoretical connection between graph convolutional networks and personalized propagation neural architectures, thereby proposing attention diffusion-prediction network (ADP-Net). This novel framework integrates three key innovations: (1) Consistent graph convolution layers with immediate attention mechanisms; (2) Multi-scale attention diffusion layers implementing graph diffusion convolution (GDC); and (3) Adaptive temporal convolution modules handling multi-timescale variations. The architecture employs polynomial approximation for GCN operations and implements an approximate personalized propagation scheme for GDC, enabling efficient multi-hop interaction modeling while maintaining structural consistency across spatial and temporal domains. Comprehensive experiments on standardized benchmarks (ETH\/UCY and Stanford Drone Dataset) show cutting-edge results, with enhancements of 4% for the average displacement error (ADE) and 26% for the final displacement error (FDE) metrics when contrasted with prior approaches. This advancement provides a robust theoretical framework and practical implementation for crowd behavior modeling in autonomous systems.<\/jats:p>","DOI":"10.3389\/frai.2025.1690704","type":"journal-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T11:52:46Z","timestamp":1764244366000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ADP-Net: a hierarchical attention-diffusion-prediction framework for human trajectory prediction"],"prefix":"10.3389","volume":"8","author":[{"given":"Zhenggui","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Shanlin","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Zhiyi","family":"Yu","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,11,27]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"961","DOI":"10.1109\/CVPR.2016.110","article-title":"\u201cSocial LSTM: human trajectory prediction in crowded spaces,\u201d","author":"Alahi","year":"2016","journal-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B2","unstructured":"\u201cOn the bottleneck of graph neural networks and its practical implications ,\u201d\n          \n          \n            \n              Alon\n              U.\n            \n            \n              Yahav\n              E.\n            \n          \n          Amherst, MA\n          OpenReview\n          Proceedings of the 9th International Conference on Learning Representations\n          \n          2021"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1294","DOI":"10.1109\/ACAIT63902.2024.11022124","article-title":"\u201cPedestrian trajectory prediction based on the view-constrained spatio-temporal graph,\u201d","author":"Chang","year":"2024","journal-title":"2024 8th Asian Conference on Artificial Intelligence Technology (ACAIT)"},{"key":"B4","doi-asserted-by":"publisher","first-page":"6923","DOI":"10.1109\/TITS.2024.3525080","article-title":"DSTIGCN: deformable spatial-temporal interaction graph convolution network for pedestrian trajectory prediction","volume":"26","author":"Chen","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LSENS.2025.3541437","article-title":"LG-STSGCN: long-term gated pedestrian trajectory prediction based on spatial-temporal synchronous graph convolutional network","volume":"9","author":"Chen","year":"2025","journal-title":"IEEE Sens. Lett"},{"key":"B6","first-page":"3837","article-title":"\u201cConvolutional neural networks on graphs with fast localized spectral filtering,\u201d","volume-title":"Advances in Neural Information Processing Systems 29","author":"Defferrard","year":"2016"},{"key":"B7","article-title":"\u201cOn over-squashing in message passing neural networks: the impact of width, depth, and topology,\u201d","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Di Giovanni","year":"2023"},{"key":"B8","doi-asserted-by":"publisher","first-page":"2188","DOI":"10.1109\/TCSVT.2024.3493966","article-title":"Recurrent aligned network for generalized pedestrian trajectory prediction","volume":"35","author":"Dong","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol"},{"key":"B9","volume-title":"Diffusion Improves Graph Learning","author":"Gasteiger","year":"2019"},{"key":"B10","doi-asserted-by":"publisher","first-page":"2255","DOI":"10.1109\/CVPR.2018.00240","article-title":"\u201cSocial gan: socially acceptable trajectories with generative adversarial networks,\u201d","author":"Gupta","year":"2018","journal-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B11","doi-asserted-by":"publisher","first-page":"16438","DOI":"10.1109\/TITS.2025.3572254","article-title":"Social entropy informer: a multi-scale model-data dual-driven approach for pedestrian trajectory prediction","volume":"26","author":"Jiang","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst"},{"key":"B12","article-title":"\u201cSemi-supervised classification with graph convolutional networks,\u201d","author":"Kipf","year":"2017","journal-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings"},{"key":"B13","article-title":"\u201cPredict then propagate: graph neural networks meet personalized pagerank,\u201d","author":"Klicpera","year":"","journal-title":"7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019"},{"key":"B14","first-page":"13333","article-title":"\u201cDiffusion improves graph learning,\u201d","author":"Klicpera","year":"","journal-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019"},{"key":"B15","doi-asserted-by":"crossref","first-page":"628","DOI":"10.1109\/ICCEA65460.2025.11103000","article-title":"\u201cPedestrian trajectory prediction based on multi-relational graph convolution and dynamic attention,\u201d","volume-title":"2025 6th International Conference on Computer Engineering and Application (ICCEA)","author":"Li","year":"2025"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1346374","DOI":"10.3389\/fnins.2024.1346374","article-title":"DTDNET: dynamic target driven network for pedestrian trajectory prediction","volume":"18","author":"Liu","year":"2024","journal-title":"Front. Neurosci"},{"key":"B17","doi-asserted-by":"publisher","first-page":"2001","DOI":"10.1109\/LRA.2023.3346806","article-title":"Stagp: spatio-temporal adaptive graph pooling network for pedestrian trajectory prediction","volume":"9","author":"Liu","year":"2024","journal-title":"IEEE Robot. Autom. Lett"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2023.3283544","article-title":"Skgacn: social knowledge-guided graph attention convolutional network for human trajectory prediction","volume":"72","author":"Lv","year":"2023","journal-title":"IEEE Trans. Instrum. Meas"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.02025","article-title":"It is not the journey but the destination: endpoint conditioned trajectory prediction","author":"Mangalam","year":"2020","journal-title":"arXiv [preprint]"},{"key":"B20","doi-asserted-by":"publisher","first-page":"14412","DOI":"10.1109\/CVPR42600.2020.01443","article-title":"\u201cSocial-stgcnn: a social spatio-temporal graph convolutional neural network for human trajectory prediction,\u201d","author":"Mohamed","year":"2020","journal-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B21","unstructured":"\u201cGraph neural networks exponentially lose expressive power for node classification,\u201d\n          \n          \n            \n              Oono\n              K.\n            \n            \n              Suzuki\n              T.\n            \n          \n          Addis Ababa\n          OpenReview\n          8th International Conference on Learning Representations (ICLR 2020)\n          \n          2020"},{"key":"B22","volume-title":"The PageRank Citation Ranking: Bringing Order to the Web (Technical Report No. 1999-66)","author":"Page","year":"1999"},{"key":"B23","doi-asserted-by":"publisher","first-page":"11809","DOI":"10.1109\/CVPR46437.2021.01164","article-title":"\u201cTrajectory prediction with latent belief energy-based model,\u201d","author":"Pang","year":"2021","journal-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B24","first-page":"8024","article-title":"\u201cPytorch: an imperative style, high-performance deep learning library,\u201d","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.07832","article-title":"Group fairness for knapsack problems","author":"Patel","year":"2020","journal-title":"arXiv [preprint]"},{"key":"B26","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1109\/ICCV.2009.5459260","article-title":"\u201cYou'll never walk alone: modeling social behavior for multi-target tracking,\u201d","volume-title":"2009 IEEE 12th International Conference on Computer Vision","author":"Pellegrini","year":"2009"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_33","article-title":"\u201cLearning social etiquette: human trajectory understanding in crowded scenes,\u201d","author":"Robicquet","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1349","DOI":"10.1109\/CVPR.2019.00144","article-title":"\u201cSophie: an attentive gan for predicting paths compliant to social and physical constraints,\u201d","author":"Sadeghian","year":"2018","journal-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B29","doi-asserted-by":"publisher","first-page":"205","DOI":"10.26599\/BDMA.2023.9020019","article-title":"Limits of depth: over-smoothing and over-squashing in GNNS","volume":"7","author":"ud din","year":"2024","journal-title":"Big Data Min. Anal"},{"key":"B30","first-page":"5998","article-title":"\u201cAttention is all you need,\u201d","volume-title":"Advances in Neural Information Processing Systems 30","author":"Vaswani","year":"2017"},{"key":"B31","unstructured":"\u201cGraph attention networks,\u201d\n          \n          \n            \n              Velickovic\n              P.\n            \n            \n              Cucurull\n              G.\n            \n            \n              Casanova\n              A.\n            \n            \n              Romero\n              A.\n            \n            \n              Li\u00f2\n              P.\n            \n            \n              Bengio\n              Y.\n            \n          \n          Vancouver, BC\n          OpenReview\n          6th International Conference on Learning Representations (ICLR 2018), Conference Track Proceedings\n          \n          2018"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1910.11945","article-title":"Improving graph attention networks with large margin-based constraints","author":"Wang","year":"2019","journal-title":"arXiv [preprint]"},{"key":"B33","doi-asserted-by":"publisher","first-page":"3089","DOI":"10.24963\/ijcai.2021\/425","article-title":"\u201cMulti-hop attention graph neural networks.\u201d","author":"Wang","year":"2021","journal-title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21), Main Track"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IJCNN55064.2022.9891949","article-title":"\u201cSocial transformer: a pedestrian trajectory prediction method based on social feature processing using transformer,\u201d","author":"Wen","year":"2022","journal-title":"2022 International Joint Conference on Neural Networks (IJCNN)"},{"key":"B35","doi-asserted-by":"publisher","first-page":"848","DOI":"10.1109\/LRA.2022.3231833","article-title":"Continual pedestrian trajectory learning with social generative replay","volume":"8","author":"Wu","year":"2023","journal-title":"IEEE Robot. Autom. Lett"},{"key":"B36","author":"Xhonneux","year":"2020"},{"key":"B37","first-page":"5453","article-title":"\u201cRepresentation learning on graphs with jumping knowledge networks,\u201d","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Xu","year":"2018"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1805","DOI":"10.1109\/TAI.2023.3299899","article-title":"Social self-attention generative adversarial networks for human trajectory prediction","volume":"5","author":"Yang","year":"2024","journal-title":"IEEE Trans. Artif. Intell"},{"key":"B39","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1109\/ICCECE65250.2025.10984993","article-title":"\u201cGraph convolutional networks with visual masking and social interaction models for pedestrian trajectory prediction,\u201d","volume-title":"2025 5th International Conference on Consumer Electronics and Computer Engineering (ICCECE)","author":"Zeng","year":"2025"},{"key":"B40","doi-asserted-by":"publisher","first-page":"2836","DOI":"10.1109\/TIV.2023.3285804","article-title":"Spatial-temporal-spectral lstm: a transferable model for pedestrian trajectory prediction","volume":"9","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Intell. Veh"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1690704\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T11:52:49Z","timestamp":1764244369000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1690704\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,27]]},"references-count":40,"alternative-id":["10.3389\/frai.2025.1690704"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1690704","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,27]]},"article-number":"1690704"}}